Multi-class sentiment analysis of urdu text using multilingual BERT

Sentiment analysis of COP9-related tweets: a comparative study of pre-trained models and traditional techniques

Introduction

Sentiment analysis has become a crucial area of research in natural language processing in recent years. The study aims to compare the performance of various sentiment analysis techniques, including lexicon-based, machine learning, Bi-LSTM, BERT, and GPT-3 approaches, using two commonly used datasets, IMDB reviews and Sentiment140. The objective is to identify the best-performing technique for an exemplar dataset, tweets associated with the WHO Framework Convention on Tobacco Control Ninth Conference of the Parties in 2021 (COP9).

Methods

A two-stage evaluation was conducted. In the first stage, various techniques were compared on standard sentiment analysis datasets using standard evaluation metrics such as accuracy, F1-score, and precision. In the second stage, the best-performing techniques from the first stage were applied to partially annotated COP9 conference-related tweets.

Results

In the first stage, BERT achieved the highest F1-scores (0.9380 for IMDB and 0.8114 for Sentiment 140), followed by GPT-3 (0.9119 and 0.7913) and Bi-LSTM (0.8971 and 0.7778). In the second stage, GPT-3 performed the best for sentiment analysis on partially annotated COP9 conference-related tweets, with an F1-score of 0.8812.

Discussion

The study demonstrates the effectiveness of pre-trained models like BERT and GPT-3 for sentiment analysis tasks, outperforming traditional techniques on standard datasets. Moreover, the better performance of GPT-3 on the partially annotated COP9 tweets highlights its ability to generalize well to domain-specific data with limited annotations. This provides researchers and practitioners with a viable option of using pre-trained models for sentiment analysis in scenarios with limited or no annotated data across different domains.

Migraine headache (MH) classification using machine learning methods with data augmentation

Migraine headache, a prevalent and intricate neurovascular disease, presents significant challenges in its clinical identification. Existing techniques that use subjective pain intensity measures are insufficiently accurate to make a reliable diagnosis. Even though headaches are a common condition with poor diagnostic specificity, they have a significant negative influence on the brain, body, and general human function. In this era of deeply intertwined health and technology, machine learning (ML) has emerged as a crucial force in transforming every aspect of healthcare, utilizing advanced facilities ML has shown groundbreaking achievements related to developing classification and automatic predictors. With this, deep learning models, in particular, have proven effective in solving complex problems spanning computer vision and data analytics. Consequently, the integration of ML in healthcare has become vital, especially in developing countries where limited medical resources and lack of awareness prevail, the urgent need to forecast and categorize migraines using artificial intelligence (AI) becomes even more crucial. By training these models on a publicly available dataset, with and without data augmentation. This study focuses on leveraging state-of-the-art ML algorithms, including support vector machine (SVM), K-nearest neighbors (KNN), random forest (RF), decision tree (DST), and deep neural networks (DNN), to predict and classify various types of migraines. The proposed models with data augmentations were trained to classify seven various types of migraine. The proposed models with data augmentations were trained to classify seven various types of migraine. The revealed results show that DNN, SVM, KNN, DST, and RF achieved an accuracy of 99.66%, 94.60%, 97.10%, 88.20%, and 98.50% respectively with data augmentation highlighting the transformative potential of AI in enhancing migraine diagnosis.

Correcting spelling mistakes in Persian texts with rules and deep learning methods

This study aims to develop a system for automatically correcting spelling errors in Persian texts using two approaches: one that relies on rules and a common spelling mistake list and another that uses a deep neural network. The list of 700 common misspellings was compiled, and a database of 55,000 common Persian words was used to identify spelling errors in the rule-based approach. 112 rules were implemented for spelling correction, each providing suggested words for misspelled words. 2500 sentences were used for evaluation, with the word with the shortest Levenshtein distance selected for evaluation. In the deep learning approach, a deep encoder-decoder network that utilized long short-term memory (LSTM) with a word embedding layer was used as the base network, with FastText chosen as the word embedding layer. The base network was enhanced by adding convolutional and capsule layers. A database of 1.2 million sentences was created, with 800,000 for training, 200,000 for testing, and 200,000 for evaluation. The results showed that the network's performance with capsule and convolutional layers was similar to that of the base network. The network performed well in evaluation, achieving accuracy, precision, recall, F-measure, and bilingual evaluation understudy (Bleu) scores of 87%, 70%, 89%, 78%, and 84%, respectively.

Roman Urdu Hate Speech Detection Using Transformer-Based Model for Cyber Security Applications

Social media applications, such as Twitter and Facebook, allow users to communicate and share their thoughts, status updates, opinions, photographs, and videos around the globe. Unfortunately, some people utilize these platforms to disseminate hate speech and abusive language. The growth of hate speech may result in hate crimes, cyber violence, and substantial harm to cyberspace, physical security, and social safety. As a result, hate speech detection is a critical issue for both cyberspace and physical society, necessitating the development of a robust application capable of detecting and combating it in real-time. Hate speech detection is a context-dependent problem that requires context-aware mechanisms for resolution. In this study, we employed a transformer-based model for Roman Urdu hate speech classification due to its ability to capture the text context. In addition, we developed the first Roman Urdu pre-trained BERT model, which we named BERT-RU. For this purpose, we exploited the capabilities of BERT by training it from scratch on the largest Roman Urdu dataset consisting of 173,714 text messages. Traditional and deep learning models were used as baseline models, including LSTM, BiLSTM, BiLSTM + Attention Layer, and CNN. We also investigated the concept of transfer learning by using pre-trained BERT embeddings in conjunction with deep learning models. The performance of each model was evaluated in terms of accuracy, precision, recall, and F-measure. The generalization of each model was evaluated on a cross-domain dataset. The experimental results revealed that the transformer-based model, when directly applied to the classification task of the Roman Urdu hate speech, outperformed traditional machine learning, deep learning models, and pre-trained transformer-based models in terms of accuracy, precision, recall, and F-measure, with scores of 96.70%, 97.25%, 96.74%, and 97.89%, respectively. In addition, the transformer-based model exhibited superior generalization on a cross-domain dataset.

Contextually Enriched Meta-Learning Ensemble Model for Urdu Sentiment Analysis

The task of analyzing sentiment has been extensively researched for a variety of languages. However, due to a dearth of readily available Natural Language Processing methods, Urdu sentiment analysis still necessitates additional study by academics. When it comes to text processing, Urdu has a lot to offer because of its rich morphological structure. The most difficult aspect is determining the optimal classifier. Several studies have incorporated ensemble learning into their methodology to boost performance by decreasing error rates and preventing overfitting. However, the baseline classifiers and the fusion procedure limit the performance of the ensemble approaches. This research made several contributions to incorporate the symmetries concept into the deep learning model and architecture: firstly, it presents a new meta-learning ensemble method for fusing basic machine learning and deep learning models utilizing two tiers of meta-classifiers for Urdu. The proposed ensemble technique combines the predictions of both the inter- and intra-committee classifiers on two separate levels. Secondly, a comparison is made between the performance of various committees of deep baseline classifiers and the performance of the suggested ensemble Model. Finally, the study’s findings are expanded upon by contrasting the proposed ensemble approach efficiency with that of other, more advanced ensemble techniques. Additionally, the proposed model reduces complexity, and overfitting in the training process. The results show that the classification accuracy of the baseline deep models is greatly enhanced by the proposed MLE approach.

Data augmentation and deep neural networks for the classification of Pakistani racial speakers recognition

Speech emotion recognition (SER) systems have evolved into an important method for recognizing a person in several applications, including e-commerce, everyday interactions, law enforcement, and forensics. The SER system's efficiency depends on the length of the audio samples used for testing and training. However, the different suggested models successfully obtained relatively high accuracy in this study. Moreover, the degree of SER efficiency is not yet optimum due to the limited database, resulting in overfitting and skewing samples. Therefore, the proposed approach presents a data augmentation method that shifts the pitch, uses multiple window sizes, stretches the time, and adds white noise to the original audio. In addition, a deep model is further evaluated to generate a new paradigm for SER. The data augmentation approach increased the limited amount of data from the Pakistani racial speaker speech dataset in the proposed system. The seven-layer framework was employed to provide the most optimal performance in terms of accuracy compared to other multilayer approaches. The seven-layer method is used in existing works to achieve a very high level of accuracy. The suggested system achieved 97.32% accuracy with a 0.032% loss in the 75%:25% splitting ratio. In addition, more than 500 augmentation data samples were added. Therefore, the proposed approach results show that deep neural networks with data augmentation can enhance the SER performance on the Pakistani racial speech dataset.